| | |
|---|
| | | import string |
|---|
| | | import logging |
|---|
| | | import os.path |
|---|
| | | import numpy as np |
|---|
| | | from tqdm import tqdm |
|---|
| | | from omegaconf import DictConfig, OmegaConf, ListConfig |
|---|
| | | |
|---|
| | |
|---|
| | | self.punc_kwargs = punc_kwargs |
|---|
| | | self.spk_model = spk_model |
|---|
| | | self.spk_kwargs = spk_kwargs |
|---|
| | | self.model_path = kwargs.get("model_path", "./") |
|---|
| | | self.model_path = kwargs.get("model_path") |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | def build_model(self, **kwargs): |
|---|
| | |
|---|
| | | for _b in range(len(speech_j)): |
|---|
| | | vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0, |
|---|
| | | sorted_data[beg_idx:end_idx][_b][0][1]/1000.0, |
|---|
| | | speech_j[_b]]] |
|---|
| | | np.array(speech_j[_b])]] |
|---|
| | | segments = sv_chunk(vad_segments) |
|---|
| | | all_segments.extend(segments) |
|---|
| | | speech_b = [i[2] for i in segments] |
|---|
| | |
|---|
| | | if self.punc_model is not None: |
|---|
| | | self.punc_kwargs.update(cfg) |
|---|
| | | punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg) |
|---|
| | | result["text_with_punc"] = punc_res[0]["text"] |
|---|
| | | result["text"] = punc_res[0]["text"] |
|---|
| | | |
|---|
| | | # speaker embedding cluster after resorted |
|---|
| | | if self.spk_model is not None: |
|---|
